From 3df5df2db4a9b09cb9d704cbf82eb747ef054b62 Mon Sep 17 00:00:00 2001 From: Emmanuel Di Pretoro Date: Fri, 24 Aug 2018 13:42:24 +0200 Subject: [PATCH] Adding the 'extract URLs' feature to the workflow --- Makefile | 3 +++ 1 file changed, 3 insertions(+) diff --git a/Makefile b/Makefile index 109435a..5c29f50 100644 --- a/Makefile +++ b/Makefile @@ -4,3 +4,6 @@ help: pdftotext: @find ./data -iname '*.pdf' -execdir pdftotext {} \; @find ./data -not \( -path ./data/text -prune \) -iname '*.txt' -exec mv {} './data/text/' ';' + +extract: + @perl extract_urls.pl data/text/*.txt